基于条件生成对抗网络的低照度彩色图像增强算法  

Low-light color image enhancement algorithm based on conditional generative adversarial network

作　　者：王珏 洪敏轩 夏叶桐 徐秀钰 孔筱芳 万敏杰 WANG Jue;HONG Minxuan;XIA Yetong;XU Xiuyu;KONG Xiaofang;WAN Minjie(School of Electronic and Optical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China;Jiangsu Key Laboratory of Spectral Imaging&Intelligent Sense,Nanjing University of Science and Technology,Nanjing 210094,China;Advanced Interdisciplinary Research Center for Optics,Nanjing University of Science and Technology,Nanjing 210094,China;National Key Laboratory of Transient Physics,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]南京理工大学电子工程与光电技术学院,江苏南京210094 [2]南京理工大学江苏省光谱成像与智能感知重点实验室,江苏南京210094 [3]南京理工大学光学前沿交叉研究中心,江苏南京210094 [4]南京理工大学瞬态物理全国重点实验室,江苏南京210094

出　　处：《红外与激光工程》2024年第11期308-321,共14页Infrared and Laser Engineering

基　　金：国家自然科学基金项目(62201260);中央高校基本科研业务费专项(30923011015,30924010941);南京理工大学本科生科研训练计划立项资助(202310288185Y)。

摘　　要：针对低照度条件下的彩色图像增强问题,提出一种基于条件生成对抗网络(Conditional Generative Adversarial Network,CGAN)的低照度图像增强算法。首先,设计了集成密集连接残差模块和注意力机制模块的生成器网络,更加关注低照度图像中的重要目标特征;然后,构建了基于选择性卷积核的判别器网络,使得判别器能够根据输入自适应地调整其感受野大小;接着,通过设计Prewitt边缘损失项和YUV色度损失项分别增强了网络模型对于图像边缘细节的提取能力和对图像色彩畸变的消除能力;最后,在LOL公开数据集上对文中算法分别进行了定性和定量测试。实验结果表明:与目前基于深度学习的低照度彩色图像增强算法相比,文中算法在峰值信噪比(Peak Signal-to-Noise Ratio,PSNR)、结构相似度(Structure Similarity Index Measure,SSIM)和色差(Color Difference,CD)等指标上分别提升了32.7%、57.5%和48.45%,能够较好地克服低照度成像条件下的图像噪声与色偏干扰问题。Objective With the rapid development of photographic and photographic equipment,it has become easier for people to obtain full-color high-definition images and video data in different scenes.Low illumination image enhancement has gradually become one of the most frontier issues in the field of night vision imaging and detection.Exploring low illumination image enhancement methods with high fidelity and high operational efficiency is of great value in military reconnaissance,emergency search and rescue,public safety and other fields.However,achieving real-time full-color low-light images under low-light imaging conditions still poses significant challenges,typically including long exposure time,low image contrast,significant loss of detail,and severe noise contamination.To solve the problem of color image enhancement under low illumination condition,a low illumination image enhancement algorithm based on conditional generative adversarial network(CGAN)is proposed.Methods CGAN utilizes an adversarial process to build a model,and takes the random noise and the preprocessed low illumination images as the input to the generator,and then generates the generated images which are as close as possible to the normal illumination through the generator network.Then the normal illumination images and the generated images are input into the discriminator at the same time,and the discriminator network is utilized to output the probability value between 0 and 1,and the parameters are updated by the computational error(Fig.1).Secondly,in order to avoid the problem of gradient vanishing due to too deep network structure,the generative network introduces the residual-in-residual dense block(RRDB)module(Fig.4).The RRDB module contains three residual dense block modules(Fig.5),each of which contains five layers of convolutional networks,and the low illuminance image features extracted by each layer of the convolutional network are supplied to the subsequent convolutional layers,allowing the feature signals to be arbitrarily propagate

关 键 词：密集连接残差 注意力机制 CGAN 低照度成像 彩色图像增强 

分 类 号：TN223[电子电信—物理电子学]